#3636th of 105 in ML frameworks and librariesFor science, health and research
isaaclab
Robot learning framework for RL and imitation learning in GPU simulation
- Stars
- 8.4k
- License
- BSD-3-Clause
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
6,746 on 1 Apr 20268,405 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Isaac Lab is a Python framework for robotics research that runs reinforcement learning, imitation learning and post-training in GPU-accelerated simulation. It supports Newton, OVRTX, OVPhysX and NVIDIA Isaac Sim as physics and rendering backends, and ships more than 16 robot models and more than 30 environments. Environments train with RSL RL, SKRL, RL Games or Stable Baselines, plus multi-agent RL.
Who it is for: Robotics researchers training RL and imitation policies in simulation
Strengths
- More than 30 ready-to-train environments and 16+ robot models, from manipulators to humanoids
- Works with RSL RL, SKRL, RL Games and Stable Baselines, and supports multi-agent RL
- Sensor simulation covers RTX cameras, LIDAR, IMU, contact sensors and ray casters
- Multiple backends; kit-less Newton workflows do not need Isaac Sim
Weaknesses
- Isaac Sim workflows need a matching Isaac Sim version (6.2 for main) and carry proprietary license terms
- The isaaclab_mimic extension is Apache 2.0 and requires cuRobo, which is proprietary
- Not a general ML library; scope is limited to robotics simulation and learning
- Hardware requirements such as RAM and VRAM are not stated in the README
What it needs
- GPU required
- Docker + Compose
- Needs NVIDIA Isaac Sim 6.2 (for Isaac Sim workflows), Newton, OVRTX, OVPhysX, cuRobo (isaaclab_mimic)
- Models: RSL RL, SKRL, RL Games, Stable Baselines
Also in ML frameworks and libraries
See all 105| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |